Unmanned aerial vehicle aerial image target detection method based on improved YOLO V5

Abstract

The invention discloses an unmanned aerial vehicle aerial image target detection method based on improved YOLO V5, and belongs to the field of deep learning and target detection. The method comprises the following steps: constructing a related data set by using aerial images of an unmanned aerial vehicle; secondly, replacing a slice layer in a Focus module by using a convolutional layer in a YOLO V5 backbone network part; using the Neck part to further process the image features; then, for the problems of target stray distribution and too small target pixel ratio caused by a high-altitude aerial photography view angle of the unmanned aerial vehicle, optimizing and eliminating a 76 * 76 * 255 large detection head in a network prediction layer part, and adjusting an anchor frame at the same time; and finally, evaluating target detection performance through generalization intersection-union ratio, average precision and reasoning speed. According to the method, on the basis of improving the recognition accuracy and the feature extraction performance, the unmanned aerial vehicle aerial image target can be rapidly and accurately detected.

Description

technical field [0001] The invention relates to an improved YOLO V5-based target detection method for aerial images of unmanned aerial vehicles, belonging to the technical field of deep learning and target detection. Background technique [0002] The intelligent perception of drone images can not only efficiently extract ground object information, but also expand the scene understanding ability of drones, and provide technical support for autonomous detection and flight of drones. Target detection is one of the key technologies to improve the intelligent perception of UAV images. However, UAV aerial images generally have the characteristics of complex background, dense distribution of targets, small scale, and large angle differences of the same category of targets. The traditional "manual feature extraction + classifier-based" target detection algorithm can no longer meet the detection accuracy requirements in complex environments and multi-scales. With the high efficiency...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem that YOLO V5 is applied to the target detection of UAV aerial images because the detection targets are aggregated into small targets, which makes the detection difficult, and the backbone network is complicated, resulting in insufficient real-time performance. YOLO V5's UAV aerial photography target detection method, which can improve the YOLO V5 backbone network architecture on the premise of improving the accuracy of the original YOLO V5, lightweight its network model, improve its reasoning speed, and achieve fast and accurate UAV Aerial Object Detection

Images